Copertina

Separations in the Representational Capabilities of Transformers and Recurrent Architectures

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bhattamishra, Satwik, Hahn, Michael, Blunsom, Phil, Kanade, Varun
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Hardness of Learning Regular Languages in the Next Symbol Prediction Setting
di: Bhattamishra, Satwik, et al.
Pubblicazione: (2025)

Provably Learning Attention with Queries
di: Bhattamishra, Satwik, et al.
Pubblicazione: (2026)

Discovering Interpretable Algorithms by Decompiling Transformers to RASP
di: Huang, Xinting, et al.
Pubblicazione: (2026)

A Formal Framework for Understanding Length Generalization in Transformers
di: Huang, Xinting, et al.
Pubblicazione: (2024)

Benefits and Limitations of Communication in Multi-Agent Reasoning
di: Rizvi-Martel, Michael, et al.
Pubblicazione: (2025)

Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
di: London, Charles, et al.
Pubblicazione: (2025)

The Transformer Cookbook
di: Yang, Andy, et al.
Pubblicazione: (2025)

Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization
di: Agrawal, Amey, et al.
Pubblicazione: (2023)

How Global Calibration Strengthens Multiaccuracy
di: Casacuberta, Sílvia, et al.
Pubblicazione: (2025)

Emergent Stack Representations in Modeling Counter Languages Using Transformers
di: Tiwari, Utkarsh, et al.
Pubblicazione: (2025)

DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection
di: Aljaafari, Tala, et al.
Pubblicazione: (2025)

Why are Sensitive Functions Hard for Transformers?
di: Hahn, Michael, et al.
Pubblicazione: (2024)

Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
di: Jobanputra, Mayank, et al.
Pubblicazione: (2025)

Gating Enables Curvature: A Geometric Expressivity Gap in Attention
di: Bathula, Satwik, et al.
Pubblicazione: (2026)

STIQ: Safeguarding Training and Inferencing of Quantum Neural Networks from Untrusted Cloud
di: Kundu, Satwik, et al.
Pubblicazione: (2024)

Inverse-Transpilation: Reverse-Engineering Quantum Compiler Optimization Passes from Circuit Snapshots
di: Kundu, Satwik, et al.
Pubblicazione: (2025)

The Effect of Architecture During Continual Learning
di: Hahn, Allyson, et al.
Pubblicazione: (2026)

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior
di: Huang, Zeyi, et al.
Pubblicazione: (2026)

IMUOptimize: A Data-Driven Approach to Optimal IMU Placement for Human Pose Estimation with Transformer Architecture
di: Ramani, Varun, et al.
Pubblicazione: (2024)

Security Concerns in Quantum Machine Learning as a Service
di: Kundu, Satwik, et al.
Pubblicazione: (2024)

Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
di: Huang, Xinting, et al.
Pubblicazione: (2025)

Explainable Machine Learning for Pediatric Dental Risk Stratification Using Socio-Demographic Determinants
di: Kanade, Manasi, et al.
Pubblicazione: (2026)

BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
di: Zhang, Qizhen, et al.
Pubblicazione: (2024)

CART: Context-Anchored Recurrent Transformer -- A Parameter-Efficient Architecture with Learned Stability
di: Capps, Chad A.
Pubblicazione: (2026)

An AI Architecture with the Capability to Explain Recognition Results
di: Whitten, Paul, et al.
Pubblicazione: (2024)

Recoverability Has a Law: The ERR Measure for Tool-Augmented Agents
di: Vuddanti, Sri Vatsa, et al.
Pubblicazione: (2026)

DyPP: Dynamic Parameter Prediction to Accelerate Convergence of Variational Quantum Algorithms
di: Kundu, Satwik, et al.
Pubblicazione: (2023)

Compact Recurrent Transformer with Persistent Memory
di: Mucllari, Edison, et al.
Pubblicazione: (2025)

Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations
di: Dhanraj, Varun, et al.
Pubblicazione: (2025)

Recurrent Joint Embedding Predictive Architecture with Recurrent Forward Propagation Learning
di: Velarde, Osvaldo M, et al.
Pubblicazione: (2024)

ASIDE: Architectural Separation of Instructions and Data in Language Models
di: Zverev, Egor, et al.
Pubblicazione: (2025)

Recurrent Action Transformer with Memory
di: Cherepanov, Egor, et al.
Pubblicazione: (2023)

Evaluating Efficacy of Model Stealing Attacks and Defenses on Quantum Neural Networks
di: Kundu, Satwik, et al.
Pubblicazione: (2024)

Adversarial Threats in Quantum Machine Learning: A Survey of Attacks and Defenses
di: Ghosh, Archisman, et al.
Pubblicazione: (2025)

The Radio-Frequency Transformer for Signal Separation
di: Lifar, Egor, et al.
Pubblicazione: (2026)

Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Search
di: Cassimon, Amber, et al.
Pubblicazione: (2024)

A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures
di: Hoang, Nhat M., et al.
Pubblicazione: (2025)

Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
di: Amiri, Alireza, et al.
Pubblicazione: (2025)

The Recurrent Transformer: Greater Effective Depth and Efficient Decoding
di: Oncescu, Costin-Andrei, et al.
Pubblicazione: (2026)

Two-Scale Latent Dynamics for Recurrent-Depth Transformers
di: Pappone, Francesco, et al.
Pubblicazione: (2025)